Not inference for graphical models, but graphical inference.
Buja, A., Cook, D., Hofmann, H., Lawrence, M., Lee, E. K., Swayne, D. F., & Wickham, H. (2009). Statistical inference for exploratory data analysis and model diagnostics. Philosophical Transactions of the Royal Society A, 367(1906), 4361–4383. doi:10.1098/rsta.2009.0120
Wickham, H., Cook, D., Hofmann, H., & Buja, A. (2010). Graphical inference for infovis. IEEE Transactions on Visualization and Computer Graphics, 16(6), 973–979. doi:10.1109/TVCG.2010.161
A general method of graphical inference: make a plot that should reveal whatever phenomenon you’re interested, and then hide it amidst many other plots generated from the null. Led to the nullabor R package.
Loy, A., Follett, L., & Hofmann, H. (2016). Variations of Q-Q Plots: The Power of Our Eyes! The American Statistician, 70(2), 202–214. doi:10.1080/00031305.2015.1077728
Uses graphical inference to test for normality using Q-Q plots, and even compares power to classical tests by using a Mechanical Turk study. Finds that graphical tests have several times the power, but comparable error rates.
Wild, C. J., Pfannkuch, M., Regan, M., & Horton, N. J. (2011). Towards more accessible conceptions of statistical inference [with discussion]. Journal of the Royal Statistical Society Series A (Statistics in Society), 174(2), 247–295. doi:10.1111/j.1467-985X.2010.00678.x
Discusses introducing the core concepts of statistical inference using entirely visual methods. (See Teaching statistics for more discussion.)